Stage 8: Choosing the lever
Prompting vs RAG vs fine-tuning, and how to fine-tune when you need to.
Summary, rules and context: AI Engineering Guide, Stage 8.
Learn
Curriculum lessons, in reading order.
Apply
Field-manual scenarios: implementation steps, an example, trade-offs, production notes, a checklist and metrics.
fine-tuning/
- Fine-tuning → SFT (supervised fine-tuning)
- Fine-tuning → PEFT / LoRA / QLoRA
- Fine-tuning → Preference tuning (DPO / RLHF)
- Fine-tuning → Distillation
- Fine-tuning → When not to fine-tune
- Fine-tuning → Ops (datasets, checkpoints, reproducibility)
Previous: Stage 7: Tools, agents and memory · Next: Stage 9: Evaluation